Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 6086 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1430. Min Act: -0.0000

Data Index: 605576 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1324. Min Act: -0.0000

Data Index: 911591 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1119. Min Act: -0.0000

Data Index: 540452 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0994. Min Act: -0.0000

Data Index: 578839 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0997. Min Act: -0.0000

Data Index: 536954 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0960. Min Act: -0.0000

Data Index: 1294316 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0887. Min Act: -0.0000

Data Index: 964298 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1345038 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0869. Min Act: -0.0000

Data Index: 215183 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0879. Min Act: -0.0000

Data Index: 38889 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0853. Min Act: -0.0000

Data Index: 6420 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0838. Min Act: -0.0000

Data Index: 514083 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0836. Min Act: -0.0000

Data Index: 77383 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0863. Min Act: -0.0000

Data Index: 699548 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0821. Min Act: -0.0000

Data Index: 653018 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0810. Min Act: -0.0000

Data Index: 902912 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0816. Min Act: -0.0000

Data Index: 931274 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0820. Min Act: -0.0000

Data Index: 7748 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1233919 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0787. Min Act: -0.0000

Data Index: 805893 (C4 (Web Text))

Max Activating Token Index: 365